How to use

ClusterFactory

in

com.oculusinfo.ml.unsupervised.cluster

  /***
   * Public method for creating a new cluster instance. The new cluster is associated with
   * the centroids for each feature.
   * 
   * @return the new cluster instance
   */
  public Cluster createCluster() {
    return (new ClusterFactory(this.typeDefs, onlineUpdate)).create();
  }
}

@Override
public Map<String, Instance> call(Tuple2<String, Instance> instance) throws Exception {
  Map<String, Instance> result = new HashMap<String, Instance>();
  Cluster c = clusterFactory.create();
  c.add(instance._2);
  result.put(c.getId(), c);
  return result;
}

ClusterFactory clusterFactory = new ClusterFactory(this.typeDefs, this.onlineUpdate);

@Override
public Instance call(Instance inst1, Instance inst2) throws Exception {
  Cluster c = clusterFactory.create();
  
  // aggregate inst1 and inst2 in a cluster
  updateCluster(inst1, c);
  updateCluster(inst2, c);

  return c;
}

ClusterFactory clusterFactory = new ClusterFactory(this.typeDefs, this.onlineUpdate);

@Override
public Iterable<Instance> call(Iterator<Tuple2<String, Instance>> instances) throws Exception {
  Map<String, Instance> clusters = new HashMap<String, Instance>();
  
  BestClusterFunction bestClusterFunc = new BestClusterFunction(distFunc, clusters, threshold);
  
  while (instances.hasNext()) {
    Tuple2<String, Instance> inst = instances.next();
    
    Tuple2<String, Instance> result = bestClusterFunc.call(inst);
  
    Cluster c;
    if (result._1 == null) {
      c = clusterFactory.create();
      clusters.put(c.getId(), c);
    }
    else {
      c = (Cluster)clusters.get(result._1);
    }
    c.add(inst._2);
  }
  return clusters.values();
}

@Override
public SparkClusterResult doCluster(DataSet ds) {
  distFunc = new DistanceFunction(this.typeDefs);
  clusterFactory = new ClusterFactory(this.typeDefs, this.onlineUpdate);

  @Override
  public Map<String, Instance> call(Tuple2<String, Instance> inst) throws Exception {
    Instance bestCluster = null;
    double bestScore = Double.MAX_VALUE;
    
    for (String clusterId : clusters.keySet()) {
      Instance cluster = clusters.get(clusterId);
      double d = distFunc.distance(inst._2, cluster);
    
      if (d < bestScore && d < threshold) {
        bestScore = d;
        bestCluster = cluster;
      }
    }
    Map<String, Instance> result = new HashMap<String, Instance>();
    if (bestCluster == null) {
      Cluster c = clusterFactory.create();
      c.add(inst._2);
      result.put(c.getId(), c);
    }
    else {
      result.put(bestCluster.getId(), bestCluster);
    }
    return result;
  }
}